首先打開起點中文網，網址為：https://www.qidian.com/
本次實戰目標是爬取一本名叫《大千界域》的小說，本次實戰僅供交流學習，支持作者，請上起點中文網訂閱觀看。
我們首先找到該小說的章節信息頁面，網址為：https://book.qidian.com/info/3144877#Catalog
點擊檢查，獲取頁面的html信息，我發現每一章都對應一個url鏈接，故我們只要得到本頁面html信息，然后通過Beautifulsoup，re等工具，就可將所有章節的url全部得到存成一個url列表然后挨個訪問便可獲取到所有章節內容，本次爬蟲也就大功告成了！
按照我的想法，我用如下代碼獲取了頁面html，並在后端輸出顯示，結果發現返回的html信息不全，包含章節鏈接的body標簽沒有被爬取到，就算補全了headers信息，還是無法獲取到body標簽里的內容，看來起點對反爬做的措施不錯嘛，這條道走不通，咱們換一條。
import requests
def get():
url = 'https://book.qidian.com/info/3144877#Catalog'
req = requests.get(url)
print(req.text)
if __name__ == '__main__':
get()
既然這個頁面是動態加載的，故可能應用ajax與后端數據庫進行了數據交互，然后渲染到了頁面上，我們只需攔截這次交互請求，獲取到交互的數據即可。
打開網頁https://book.qidian.com/info/3144877#Catalog，再次右鍵點擊檢查即審查元素，因為是要找到數據交互，故點擊network里的XHR請求，精確捕獲XHR對象，我們發現一個url為https://book.qidian.com/ajax/book/category?_csrfToken=1iiVodIPe2qL9Z53jFDIcXlmVghqnB6jSwPP5XKF&bookId=3144877的請求返回的response是一個包含所有卷id和章節id的json對象，這就是我們要尋找的交互數據。
通過如下代碼，便可獲取到該json對象
import requests
import random
def random_user_agent():
list = ['Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML like Gecko) Chrome/44.0.2403.155 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2226.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.4; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36']
seed = random.randint(0, len(list)-1)
return list[seed]
def getJson():
url = 'https://book.qidian.com/ajax/book/category?_csrfToken=BXnzDKmnJamNAgLu4O3GknYVL2YuNX5EE86tTBAm&bookId=3144877'
headers = {'User-Agent': random_user_agent(),
'Referer': 'https://book.qidian.com/info/3144877',
'Cookie': '_csrfToken=BXnzDKmnJamNAgLu4O3GknYVL2YuNX5EE86tTBAm; newstatisticUUID=1564467217_1193332262; qdrs=0%7C3%7C0%7C0%7C1; showSectionCommentGuide=1; qdgd=1; lrbc=1013637116%7C436231358%7C0%2C1003541158%7C309402995%7C0; rcr=1013637116%2C1003541158; bc=1003541158%2C1013637116; e1=%7B%22pid%22%3A%22qd_P_limitfree%22%2C%22eid%22%3A%22qd_E01%22%2C%22l1%22%3A4%7D; e2=%7B%22pid%22%3A%22qd_P_free%22%2C%22eid%22%3A%22qd_A18%22%2C%22l1%22%3A3%7D'
}
res = requests.get(url=url, params=headers)
json_str = res.text
print(json_str)
if __name__ == '__main__':
getJson()
在小說的章節信息頁面里我發現有分卷閱讀，點擊進入后發現該頁面包含該卷的所有章節內容，且每一個分卷閱讀的前半段url都是https://read.qidian.com/hankread/3144877/，變得只是該卷的id號，例如第一卷初來乍到的id為8478272，故閱讀整個第一卷內容的鏈接為https://read.qidian.com/hankread/3144877/8478272。故我們只需要在上述json對象里截取所有卷id，便可以爬取整本了！
爬取效果如下：
完整代碼如下：
import requests
import re
from bs4 import BeautifulSoup
from requests.exceptions import *
import random
import json
import time
import os
import sys
def random_user_agent():
list = ['Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML like Gecko) Chrome/44.0.2403.155 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2226.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.4; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36']
seed = random.randint(0, len(list)-1)
return list[seed]
def getJson():
url = 'https://book.qidian.com/ajax/book/category?_csrfToken=BXnzDKmnJamNAgLu4O3GknYVL2YuNX5EE86tTBAm&bookId=3144877'
headers = {'User-Agent': random_user_agent(),
'Referer': 'https://book.qidian.com/info/3144877',
'Cookie': '_csrfToken=BXnzDKmnJamNAgLu4O3GknYVL2YuNX5EE86tTBAm; newstatisticUUID=1564467217_1193332262; qdrs=0%7C3%7C0%7C0%7C1; showSectionCommentGuide=1; qdgd=1; lrbc=1013637116%7C436231358%7C0%2C1003541158%7C309402995%7C0; rcr=1013637116%2C1003541158; bc=1003541158%2C1013637116; e1=%7B%22pid%22%3A%22qd_P_limitfree%22%2C%22eid%22%3A%22qd_E01%22%2C%22l1%22%3A4%7D; e2=%7B%22pid%22%3A%22qd_P_free%22%2C%22eid%22%3A%22qd_A18%22%2C%22l1%22%3A3%7D'
}
try:
res = requests.get(url=url, params=headers)
if res.status_code == 200:
json_str = res.text
list = json.loads(json_str)['data']['vs']
response = {
'VolumeId_List': [],
'VolumeNum_List': []
}
for i in range(len(list)):
json_str = json.dumps(list[i]).replace(" ", "")
volume_id = re.search('.*?"vId":(.*?),', json_str, re.S).group(1)
volume_num = re.search('.*?"cCnt":(.*?),', json_str, re.S).group(1)
response['VolumeId_List'].append(volume_id)
response['VolumeNum_List'].append(volume_num)
return response
else:
print('No response')
return None
except ReadTimeout:
print("ReadTimeout!")
return None
except RequestException:
print("請求頁面出錯！")
return None
def getPage(VolId_List, VolNum_List):
'''
通過卷章Id找到要爬取的頁面，並返回頁面html信息
:param VolId_List: 卷章Id列表
:param VolNum_List: 每一卷含有的章節數量列表
:return:
'''
size = len(VolId_List)
for i in range(size):
path = 'C://Users//49881//Projects//PycharmProjects//Spider2起點中文網//大千界域//卷' + str(i + 1)
mkdir(path)
url = 'https://read.qidian.com/hankread/3144877/'+VolId_List[i]
print('\n當前訪問路徑：'+url)
headers = {
'User-Agent': random_user_agent(),
'Referer': 'https://book.qidian.com/info/3144877',
'Cookie': 'e1=%7B%22pid%22%3A%22qd_P_hankRead%22%2C%22eid%22%3A%22%22%2C%22l1%22%3A3%7D; e2=%7B%22pid%22%3A%22qd_P_hankRead%22%2C%22eid%22%3A%22%22%2C%22l1%22%3A2%7D; _csrfToken=BXnzDKmnJamNAgLu4O3GknYVL2YuNX5EE86tTBAm; newstatisticUUID=1564467217_1193332262; qdrs=0%7C3%7C0%7C0%7C1; showSectionCommentGuide=1; qdgd=1; e1=%7B%22pid%22%3A%22qd_P_limitfree%22%2C%22eid%22%3A%22qd_E01%22%2C%22l1%22%3A4%7D; e2=%7B%22pid%22%3A%22qd_P_free%22%2C%22eid%22%3A%22qd_A18%22%2C%22l1%22%3A3%7D; rcr=3144877%2C1013637116%2C1003541158; lrbc=3144877%7C52472447%7C0%2C1013637116%7C436231358%7C0%2C1003541158%7C309402995%7C0; bc=3144877'
}
try:
res = requests.get(url=url, params=headers)
if res.status_code == 200:
print('第'+str(i+1)+'卷已開始爬取：')
parsePage(res.text, url, path, int(VolNum_List[i]))
else:
print('No response')
return None
except ReadTimeout:
print("ReadTimeout!")
return None
except RequestException:
print("請求頁面出錯！")
return None
time.sleep(3)
def parsePage(html, url, path, chapNum):
'''
解析小說內容頁面，將每章內容寫入txt文件，並存儲到相應的卷目錄下
:param html: 小說內容頁面
:param url: 訪問路徑
:param path: 卷目錄路徑
:return: None
'''
if html == None:
print('訪問路徑為'+url+'的頁面為空')
return
soup = BeautifulSoup(html, 'lxml')
ChapInfoList = soup.find_all('div', attrs={'class': 'main-text-wrap'})
alreadySpiderNum = 0.0
for i in range(len(ChapInfoList)):
sys.stdout.write('\r已爬取{0}'.format('%.2f%%' % float(alreadySpiderNum/chapNum*100)))
sys.stdout.flush()
time.sleep(0.5)
soup1 = BeautifulSoup(str(ChapInfoList[i]), 'lxml')
ChapName = soup1.find('h3', attrs={'class': 'j_chapterName'}).span.string
ChapName = re.sub('[\/:*?"<>|]', '', ChapName)
if ChapName == '無題':
ChapName = '第'+str(i+1)+'章 無題'
filename = path+'//'+ChapName+'.txt'
readContent = soup1.find('div', attrs={'class': 'read-content j_readContent'}).find_all('p')
for item in readContent:
paragraph = re.search('.*?<p>(.*?)</p>', str(item), re.S).group(1)
save2file(filename, paragraph)
alreadySpiderNum += 1.0
sys.stdout.write('\r已爬取{0}'.format('%.2f%%' % float(alreadySpiderNum / chapNum * 100)))
def save2file(filename, content):
with open(r''+filename, 'a', encoding='utf-8') as f:
f.write(content+'\n')
f.close()
def mkdir(path):
'''
創建卷目錄文件夾
:param path: 創建路徑
:return: None
'''
folder = os.path.exists(path)
if not folder:
os.makedirs(path)
else:
print('路徑'+path+'已存在')
def main():
response = getJson()
if response != None:
VolId_List = response['VolumeId_List']
VolNum_List = response['VolumeNum_List']
getPage(VolId_List, VolNum_List)
else:
print('無法爬取該小說！')
print("小說爬取完畢!")
if __name__ == '__main__':
main()